© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101113
    Prev
    Next
    INDEX
    Explanations

    names followed by places or roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Of
    -2.59
    蛧
    -2.50
     pervasive
    -2.39
    ");
    -2.28
    錸
    -2.27
    vantaged
    -2.23
    他们的
    -2.19
    镠
    -2.17
    ).
    -2.09
     gewöhnlich
    -2.05
    POSITIVE LOGITS
    {
    3.17
    xvii
    2.55
    蚨
    2.27
    ſſen
    2.22
    with
    2.22
     spezielle
    2.20
    盞
    2.20
    を始め
    2.16
     schnelle
    2.16
    ^^
    2.16
    Activations Density 0.037%

    No Known Activations